柔性化机器人:从类人到软体课程详细信息

课程号 00333138 学分 3
英文名称 Compliant Robotics: from rigid links to soft
先修课程
中文简介 传统的工业机器人被设计成尽可能刚性,以确保良好的运动精度;然而,由于其巨大的刚性,在与人类近距
离操作时可能会造成危险。此外,随着机器人将其领域扩展到医疗保健和家庭服务领域,安全性、适应性和
能源效率成为首要问题。为了应对这些挑战,科学家们正在开发新一代顺应式机器人,从刚性连杆机器人发
展为柔性和软性机器人。本课程旨在为学生提供刚性连杆到柔性机器人建模、感知、交互控制和路径规划的
基本知识。本课程包括一个实践编码练习,以促进解决实际问题的算法的实现。
英文简介 Traditional industrial robots have been designed to be as rigid as possible to ensure good motion
precision; however, because of the massive rigidity, it can make them dangerous when operating
in close proximity with humans. Further, as robots expand their domain into healthcare and
home service, the issues of safety, adaptability and energy efficiency become a primary concern.
To address these challenges, scientists are developing a new generation of compliant robots,
evolving from rigid-link robots to flexible and soft robots. This course aims to provide students
with an essential knowledge for rigid-link to compliant robotic modeling, perception, interactive
control and path planning. This course involves a hands-on coding exercise to facilitate the implementation of algorithms for solving real-world problems.
开课院系 工学院
通选课领域  
是否属于艺术与美育
平台课性质  
平台课类型  
授课语言 英文
教材 Probabilistic Robotics,Sebastian Thrun, Wolfram Burgard, Dieter Fox,The MIT Press,2005;
Robotics: Modelling, Planning and Control,Bruno Siciliano, Lorenzo Sciavicco, Luigi Villani, Giuseppe Oriolo,Springer-Verlag London,2009;
参考书
教学大纲 Globex
Objectives:
1. Introduction of the state of the art robotic technology from humanoids to soft and flexible
robots
2. Understand and develop kinematic and dynamic models for robotic systems
3. Understand and implement different methods for estimating and control the robot
position and the interaction force
4. Understand and implement AI methods for robot path planning and learning
Topics:
1. Modeling of Different Robot Systems
1.1 Mathematical preliminaries (notation)
1.2 Rigid-link robot model
1.3 Continuum/flexible robot model
1.4 Dynamic models
2. Estimate/Perceive Robot Position/Speed/Force
2.1 Probabilistic approaches
2.2 Kalman filtering
2.3 Bayesian filtering
2.4 Gaussian mixture model
3. Robot Path Planning
3.1 Generate smooth path
3.2 Potential field
3.3 A* path planning
4. Robot Controls
4.1 State-feedback control
4.2 PID control
4.3 Impedance control
课堂讲授每周15学时,共三周45学时
Project: 3 project assignments that include a final team project presentation
2 Individual Projects @ 15% each - 30%
1 Final Teamwork Project (Team Presentation) - 30%
Final Exam - 40%
教学评估 Hongbin Liu:
学年度学期:16-17-3,课程班:柔性化机器人:从类人到软体1,课程推荐得分:null,教师推荐得分:null,课程得分分数段:80及以下;
学年度学期:17-18-3,课程班:柔性化机器人:从类人到软体1,课程推荐得分:null,教师推荐得分:null,课程得分分数段:80及以下;